Comparing SNNs and RNNs on neuromorphic vision datasets: Similarities and differences

He, Weihua; Wu, Yujie; Deng, Lei; Li, Guoqi; Wang, Haoyu; Tian, Yang; Ding, Wei; Wang, Wenhui; Xie, Yuan

doi:10.1016/j.neunet.2020.08.001

Cited by 113 publications

(49 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since we do not believe N-MNIST to encode discriminative features in time, we could then exploit such an artifact to do a rate-based classification, as we rightfully demonstrate in section 7. There are others who agree with our point of view on the limitations of datasets such as N-MNIST (for e.g., Sethi and Suri, 2019;Zhu et al, 2019;Deng et al, 2020;He et al, 2020;See et al, 2020), andHe et al (2020) shows similar results in a different paradigm (i.e., RNN vs. SNN) to further corroborate our point.…”

Section: Rd-stdp N-mnistsupporting

confidence: 90%

“…Both these advantages are discussed in work still under review. He et al (2020) show that datasets not derived from static images (i.e., DvsGesture) are more suitable for SNNs than RNNs. On the other hand, datasets such as N-MNIST do not show this advantage.…”

Section: Rd-stdp N-mnistmentioning

confidence: 98%

“…We also reasoned why our approach is generalizable to SNNs in general. While comparing RNNs and SNNs, He et al (2020) have also compared N-MNIST and DvsGesture, and also concluded that smaller time windows result in better performance for DvsGesture, but not N-MNIST.…”

Section: Rd-stdp N-mnistmentioning

confidence: 99%

See 2 more Smart Citations

Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain

Iyer

Chua

2021

Front. Neurosci.

View full text Add to dashboard Cite

A major characteristic of spiking neural networks (SNNs) over conventional artificial neural networks (ANNs) is their ability to spike, enabling them to use spike timing for coding and efficient computing. In this paper, we assess if neuromorphic datasets recorded from static images are able to evaluate the ability of SNNs to use spike timings in their calculations. We have analyzed N-MNIST, N-Caltech101 and DvsGesture along these lines, but focus our study on N-MNIST. First we evaluate if additional information is encoded in the time domain in a neuromorphic dataset. We show that an ANN trained with backpropagation on frame-based versions of N-MNIST and N-Caltech101 images achieve 99.23 and 78.01% accuracy. These are comparable to the state of the art—showing that an algorithm that purely works on spatial data can classify these datasets. Second we compare N-MNIST and DvsGesture on two STDP algorithms, RD-STDP, that can classify only spatial data, and STDP-tempotron that classifies spatiotemporal data. We demonstrate that RD-STDP performs very well on N-MNIST, while STDP-tempotron performs better on DvsGesture. Since DvsGesture has a temporal dimension, it requires STDP-tempotron, while N-MNIST can be adequately classified by an algorithm that works on spatial data alone. This shows that precise spike timings are not important in N-MNIST. N-MNIST does not, therefore, highlight the ability of SNNs to classify temporal data. The conclusions of this paper open the question—what dataset can evaluate SNN ability to classify temporal data?

show abstract

Section: Rd-stdp N-mnistsupporting

confidence: 90%

Section: Rd-stdp N-mnistmentioning

confidence: 98%

See 1 more Smart Citation

Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain

Iyer

Chua

2021

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…In addition, besides energy-efficiency (Merolla et al, 2014), recent studies further find that the event-driven computing paradigm of SNNs endows them high robustness (He et al, 2020;Liang et al, 2020) and superior capability in learning sparse features (He et al, 2020). We believe it is very important to mine the true advantages of SNNs to determine their true value in practical applications.…”

Section: Applicationsmentioning

confidence: 99%

Editorial: Understanding and Bridging the Gap Between Neuromorphic Computing and Machine Learning

Deng

Tang

Roy

2021

Front. Comput. Neurosci.

Self Cite

View full text Add to dashboard Cite

“…Many approaches based on traditional ANNs have been proposed for processing event-based images, e.g. RNN [4], DART [5], HATS [6]. Spiking neural network (SNN) is the third generation of neuron network.…”

Section: Introductionmentioning

confidence: 99%

Cascade Spiking Neuron Network For Event-based Image Classification In Noisy Environment

Han¹,

Chen²,

Cheng³

et al. 2021

Preprint

View full text Add to dashboard Cite

<div> <div> <div> <div> <p>Spiking Neuron Network (SNN) has shown advantages in processing event-based data for image classification. However, the classification accuracy of SNNs decreases in noisy environment. The cascade spiking neuron network (cascade-SNN) was proposed to solve this problem in this letter. We used spiking convolutional spiking neuron network (SCNN) for features extraction and liquid state machine (LSM) for read out. Compared with early works on ANNs, this network achieved the state-of-the-art classification accuracy in DVS-CIFAR10 dataset and DVS-Gesture dataset, which are both challenging dataset because of noisy environment. We conducted ablation experiments to verify the proposed structure is effective and analyzed the influence of different hyper-parameters. </p> </div> </div> </div> </div>

show abstract

Comparing SNNs and RNNs on neuromorphic vision datasets: Similarities and differences

Cited by 113 publications

References 39 publications

Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain

Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain

Editorial: Understanding and Bridging the Gap Between Neuromorphic Computing and Machine Learning

Cascade Spiking Neuron Network For Event-based Image Classification In Noisy Environment

Contact Info

Product

Resources

About